手法を比較

	Multimodal Multilayer Perceptron	マルチモーダル畳み込みニューラルネットワーク
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2011 (multimodal extension); 1986 (MLP backpropagation)	2011
提唱者	Ngiam et al. / Rumelhart, Hinton & Williams (MLP foundations)	Ngiam, J. et al. / multiple groups
種類	Feedforward neural network with multi-stream fusion	Multimodal deep learning model
原典	Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. In Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 689–696.	Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. In Proceedings of the 28th International Conference on Machine Learning (ICML), 689–696.
別名	MM-MLP, multimodal MLP, multi-input feedforward network, fusion multilayer perceptron	MM-CNN, multimodal CNN, multi-input CNN, cross-modal convolutional network
関連	5	5
概要	A Multimodal Multilayer Perceptron (MM-MLP) is a feedforward neural network that ingests features from two or more heterogeneous input modalities — such as structured tabular data, text embeddings, and image feature vectors — by encoding each stream separately and fusing them into a shared representation before passing it through fully connected layers to produce a classification or regression output.	A Multimodal Convolutional Neural Network (MM-CNN) processes and fuses two or more input modalities — such as images and text, or video and audio — through dedicated convolutional branches, learning a shared representation that captures complementary signals from each source. The fused representation drives a downstream task such as classification, regression, or retrieval.